Advbox: a toolbox to generate adversarial examples that fool neural networks

Abstract

In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images are sufficient to fool the most powerful neural networks. \emph{Advbox} is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle, PyTorch, Caffe2, MxNet, Keras, TensorFlow and it can benchmark the robustness of machine learning models. Compared to previous work, our platform supports black box attacks on Machine-Learning-as-a-service, as well as more attack scenarios, such as Face Recognition Attack, Stealth T-shirt, and DeepFake Face Detect. The code is licensed under the Apache 2.0 and is openly available at https://github.com/advboxes/AdvBox. Advbox now supports Python 3.

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Explaining and Harnessing Adversarial Examples
• WaveNet: A Generative Model for Raw Audio
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
• Robust Audio Adversarial Example for a Physical Attack
• HotFlip: White-Box Adversarial Examples for Text Classification
• Adversarial Examples for Semantic Image Segmentation
• Adversarial T-shirt! Evading Person Detectors in A Physical World
• Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
• Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service
• Attacking and Defending Machine Learning Applications of Public Cloud
• FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications
• Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield

Cited by in corpus (12)

• Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
• Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
• RobustBench: a standardized adversarial robustness benchmark
• OpenAttack: An Open-source Textual Adversarial Attack Toolkit
• Understanding Real-world Threats to Deep Learning Models in Android Apps
• Towards a Robust Deep Neural Network in Texts: A Survey
• DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
• Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service
• KoDF: A Large-scale Korean DeepFake Detection Dataset
• SEC4SR: A Security Analysis Platform for Speaker Recognition
• Attacking and Defending Machine Learning Applications of Public Cloud
• AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient